Hugging Face's logo

eduardopds
/
distilbert-base-uncased-tweets

Text Classification
Transformers
TensorFlow
distilbert
generated_from_keras_callback
Inference Endpoints
Model card Files Community
1
eduardopds commited on
Commit
6c6c82f
•
1 Parent(s): dd7270e

Training in progress epoch 0

Browse files
Files changed (3) hide show
  1. README.md +6 -15
  2. config.json +1 -1
  3. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.7627
18
- - Validation Loss: 0.9286
19
- - Epoch: 9
20
 
21
  ## Model description
22
 
@@ -42,21 +42,12 @@ The following hyperparameters were used during training:
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
- | 0.7575 | 0.9286 | 0 |
46
- | 0.7569 | 0.9286 | 1 |
47
- | 0.7588 | 0.9286 | 2 |
48
- | 0.7543 | 0.9286 | 3 |
49
- | 0.7570 | 0.9286 | 4 |
50
- | 0.7626 | 0.9286 | 5 |
51
- | 0.7563 | 0.9286 | 6 |
52
- | 0.7580 | 0.9286 | 7 |
53
- | 0.7581 | 0.9286 | 8 |
54
- | 0.7627 | 0.9286 | 9 |
55
 
56
 
57
  ### Framework versions
58
 
59
- - Transformers 4.19.0
60
  - TensorFlow 2.8.0
61
- - Datasets 2.2.1
62
  - Tokenizers 0.12.1
 
14
 
15
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 1.0162
18
+ - Validation Loss: 1.0010
19
+ - Epoch: 0
20
 
21
  ## Model description
22
 
 
42
 
43
  | Train Loss | Validation Loss | Epoch |
44
  |:----------:|:---------------:|:-----:|
45
+ | 1.0162 | 1.0010 | 0 |
 
 
 
 
 
 
 
 
 
46
 
47
 
48
  ### Framework versions
49
 
50
+ - Transformers 4.19.2
51
  - TensorFlow 2.8.0
52
+ - Datasets 2.2.2
53
  - Tokenizers 0.12.1
config.json CHANGED
@@ -28,6 +28,6 @@
28
  "seq_classif_dropout": 0.2,
29
  "sinusoidal_pos_embds": false,
30
  "tie_weights_": true,
31
- "transformers_version": "4.19.0",
32
  "vocab_size": 30522
33
  }
 
28
  "seq_classif_dropout": 0.2,
29
  "sinusoidal_pos_embds": false,
30
  "tie_weights_": true,
31
+ "transformers_version": "4.19.2",
32
  "vocab_size": 30522
33
  }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1f79cc041a473b33ccd80bffa9ce8ec28e590c0c84d36cb2a9a8ed92b379ee0
3
  size 267954968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f7022bab7eb0ea0342066b6731b0d93f51f9f3b0f094840e67445a07670a5e
3
  size 267954968